Development of clinical practice guidelines for patients with comorbidity and multiple diseases

Machine Learning-Based Prediction of Changes in the Clinical Condition of Patients With Complex Chronic Diseases: 2-Phase Pilot Prospective Single-Center Observational Study

BACKGROUND

Functional impairment is one of the most decisive prognostic factors in patients with complex chronic diseases. A more significant functional impairment indicates that the disease is progressing, which requires implementing diagnostic and therapeutic actions that stop the exacerbation of the disease.

OBJECTIVE

This study aimed to predict alterations in the clinical condition of patients with complex chronic diseases by predicting the Barthel Index (BI), to assess their clinical and functional status using an artificial intelligence model and data collected through an internet of things mobility device.

METHODS

A 2-phase pilot prospective single-center observational study was designed. During both phases, patients were recruited, and a wearable activity tracker was allocated to gather physical activity data. Patients were categorized into class A (BI≤20; total dependence), class B (2060; moderate or mild dependence, or independent). Data preprocessing and machine learning techniques were used to analyze mobility data. A decision tree was used to achieve a robust and interpretable model. To assess the quality of the predictions, several metrics including the mean absolute error, median absolute error, and root mean squared error were considered. Statistical analysis was performed using SPSS and Python for the machine learning modeling.

RESULTS

Overall, 90 patients with complex chronic diseases were included: 50 during phase 1 (class A: n=10; class B: n=20; and class C: n=20) and 40 during phase 2 (class B: n=20 and class C: n=20). Most patients (n=85, 94%) had a caregiver. The mean value of the BI was 58.31 (SD 24.5). Concerning mobility aids, 60% (n=52) of patients required no aids, whereas the others required walkers (n=18, 20%), wheelchairs (n=15, 17%), canes (n=4, 7%), and crutches (n=1, 1%). Regarding clinical complexity, 85% (n=76) met patient with polypathology criteria with a mean of 2.7 (SD 1.25) categories, 69% (n=61) met the frailty criteria, and 21% (n=19) met the patients with complex chronic diseases criteria. The most characteristic symptoms were dyspnea (n=73, 82%), chronic pain (n=63, 70%), asthenia (n=62, 68%), and anxiety (n=41, 46%). Polypharmacy was presented in 87% (n=78) of patients. The most important variables for predicting the BI were identified as the maximum step count during evening and morning periods and the absence of a mobility device. The model exhibited consistency in the median prediction error with a median absolute error close to 5 in the training, validation, and production-like test sets. The model accuracy for identifying the BI class was 91%, 88%, and 90% in the training, validation, and test sets, respectively.

CONCLUSIONS

Using commercially available mobility recording devices makes it possible to identify different mobility patterns and relate them to functional capacity in patients with polypathology according to the BI without using clinical parameters.

Concordance between the Clinical Definition of Polypathological Patient versus Automated Detection by Means of Combined Identification through ICD-9-CM Codes

It is unknown whether the digital application of automated ICD-9-CM codes recorded in the medical history are useful for a first screening in the detection of polypathological patients. In this study, the objective was to identify the degree of intra- and inter-observer concordance in the identification of in-patient polypathological patients between the standard clinical identification method and a new automatic method, using the basic minimum data set of ICD-9-CM codes in the digital medical history. For this, a cross-sectional multicenter study with 1518 administratively discharged patients from Andalusian hospitals during the period of 2013-2014 has been carried out. For the concordance between the clinical definition of a polypathological patient and the polypathological patient classification according to ICD-9-CM coding, a 0.661 kappa was obtained (95% confidence interval (CI); 0.622-0.701) with p < 0.0001. The intraclass correlation coefficient between both methods for the number of polypathological patient categories was 0.745 (95% CI; 0.721-0.768; p < 0.0001). The values of sensitivity, specificity, positive-, and negative predictive values of the automated detection using ICD-9-CM coding were 78%, 88%, 78%, and 88%, respectively. As conclusion, the automatic identification of polypathological patients by detecting ICD-9-CM codes is useful as a screening method for in-hospital patients.

Advanced practice in case management: An essential element in the new complex chronicity care model

The increased prevalence of complex chronic diseases in all stages of life, the progressive aging of the population, the prevalence of multimorbidity, polypharmacy, and loss of autonomy, have given rise to new needs in society. The current model of care is failing to meet these needs in an effective or sustainable way. People with complex chronic diseases are vulnerable, they deteriorate as diseases progress, and they require individualized and coordinated professional care that takes into account the progression of the disease, transitions and people's preferences. It is essential to determine a new care paradigm as a framework for the projects and actions that should be promoted to reach transversal, sustainable and quality care directed at people with complex and advanced chronic diseases in all stages of life. Different studies show that case management is an added value in terms of quality, safety and cost-effectiveness. However, its implementation in Spain is uneven and heterogeneous, and no regulations have yet been developed to give stability to this new nurse figure. The Ministry and the Autonomous Communities now have the responsibility to create regulations and institutionalize the figure of case management nurses/advanced practice nurses, with a clear definition of their professional competences and functions, as has been done in other countries.

Healthcare professionals' views of the experiences of individuals living with Crohn's Disease in Spain. A qualitative study

Crohn's Disease (CD) in Spain lacks of a unified National Clinical Pathway and not even any early detection program and professional follow-up outpatient attention once it has been diagnosed. Little is known about the Spanish health professionals' views of the experiences of individuals living with Crohn's Disease nationwide and also about how the Spanish Health System faces this situation. A qualitative research method was conducted to explore this topic through in-depth interviews with eleven healthcare professionals, who represented different clinics treating people with CD from the province of Alicante (Spain). Three topics and seven sub-topics were derived from the analysis of the content emerging from the interviews. The three main topics were: the healthcare system as a hindrance for ongoing treatment of CD, the impact of the disease, support networks. The knowledge of CD gained by healthcare professionals, in the contexts studied here within, with regards to the psychosocial aspects and the experience of those living with the disease and their immediate circles, is poor, if not null on an academic level, becoming experiential on their incorporation into the professional field. Additionally, a priori, they lack the tools to address the doubts and concerns of patients from the moment of diagnosis through the ongoing care of the patient. Organizational hindrances, such as the lack of time and consensual guidelines for adequately monitoring CD patients in Alicante (Spain), further restrict the patient-professional relationship. Due to the consensus established by the National Agency regulating the contents of the Health Professions' Education and Training across the country, we are assuming that the phenomenon highlighted may be similar in other parts of Spain. Therefore, it can be said that healthcare professionals have a limited understanding of the impact of CD on the day-to-day life of those affected, not being considered a part of the CD patients' formal support network. Nonetheless, they are conscious of this limitation and advocate for multidisciplinary teams as the best means of attending to people living with CD. Our study outcomes may represent the first step onto identifying strategies and best practices for establishing an effective therapeutic relationship, as well as any hindering factors.

Prevalence and overlap of Disease Management Program diseases in older hospitalized patients

Many countries, like Denmark, have tailored Disease Management Programs (DMPs) based on patients having single chronic diseases [defined institutionally as "program diseases" (PDs)], which can complicate treatment for those with multiple chronic diseases. The aims of this study were (a) to assess the prevalence and overlap among acutely hospitalized older medical patients of PDs defined by the DMPs, and (b) to examine transitions between different departments during hospitalization and mortality and readmission within two time intervals among patients with the different PDs. We conducted a registry study of 4649 acutely hospitalized medical patients ≥65 years admitted to Copenhagen University Hospital, Hvidovre, Denmark, in 2012, and divided patients into six PD groups (type 2 diabetes, chronic obstructive pulmonary disease, cardiovascular disease, musculoskeletal disease, dementia and cancer), each defined by several ICD-10 codes predefined in the DMPs. Of these patients, 904 (19.4%) had 2 + PDs, and there were 47 different combinations of the six different PDs. The most prevalent pair of PDs was type 2 diabetes with cardiovascular disease in 203 (22.5%) patients, of whom 40.4% had an additional PD. The range of the cumulative incidence of being readmitted within 90 days was between 28.8% for patients without a PD and 46.6% for patients with more than one PD. PDs overlapped in many combinations, and all patients had a high probability of being readmitted. Hence, developing strategies to create a new generation of DMPs applicable to older patients with comorbidities could help clinicians organize treatment across DMPs.

CRONIGAL: Prognostic index for chronic patients after hospital admission

OBJECTIVE

We have followed patients admitted to a Polypathology and Advanced Age Unit for two years in order to identify the variables that best define the mortality prognosis at medium-term (1-2years) for chronic and polypathological patients requiring admission at an Internal Medicine Department.

METHODS

This is an observational, prospective study in clinical practice. Polypathological, chronic or multimorbidity patients were included. The classification of the Spanish Ministry for Health was used in order to classify patients as chronic or polypathological. The Charlson Index and Barthel Index were estimated and the Pfeiffer test was administered. The Spanish PROFUND Index was also used. Logistic regression models and Cox proportional hazard model were built in order to study the influence of prognostic factors on survival.

RESULTS

A total of 567 patients were included: 333 met polypathological (PPP) criteria and 234 chronic criteria (CC). Mean age was 84.8+7.3years. A total of 469 were followed up, most patients belonged to category E (282), 174 to category A and 118 to category C. The prognosis at one year of our patients can be estimated with 7 variables: age, neoplasia, delirium, Barthel, Pfeiffer, presence of atrial fibrillation, and creatinine. The area under the curve is 0.74.

CONCLUSION

The variables dementia, neoplasia, delirium at admission, Barthel Index under 60, or deceased spouse have mortality prognosis value at one or two years. An index with 7 variables applicable to chronic and polypathological patients after admission may serve as tool to better manage complex chronic patients and follow them up.

Multimorbidity in chronic disease: impact on health care resources and costs

Effective and resource-efficient long-term management of multimorbidity is one of the greatest health-related challenges facing patients, health professionals, and society more broadly. The purpose of this review was to provide a synthesis of literature examining multimorbidity and resource utilization, including implications for cost-effectiveness estimates and resource allocation decision making. In summary, previous literature has reported substantially greater, near exponential, increases in health care costs and resource utilization when additional chronic comorbid conditions are present. Increased health care costs have been linked to elevated rates of primary care and specialist physician occasions of service, medication use, emergency department presentations, and hospital admissions (both frequency of admissions and bed days occupied). There is currently a paucity of cost-effectiveness information for chronic disease interventions originating from patient samples with multimorbidity. The scarcity of robust economic evaluations in the field represents a considerable challenge for resource allocation decision making intended to reduce the burden of multimorbidity in resource-constrained health care systems. Nonetheless, the few cost-effectiveness studies that are available provide valuable insight into the potential positive and cost-effective impact that interventions may have among patients with multiple comorbidities. These studies also highlight some of the pragmatic and methodological challenges underlying the conduct of economic evaluations among people who may have advanced age, frailty, and disadvantageous socioeconomic circumstances, and where long-term follow-up may be required to directly observe sustained and measurable health and quality of life benefits. Research in the field has indicated that the impact of multimorbidity on health care costs and resources will likely differ across health systems, regions, disease combinations, and person-specific factors (including social disadvantage and age), which represent important considerations for health service planning. Important priorities for research include economic evaluations of interventions, services, or health system approaches that can remediate the burden of multimorbidity in safe and cost-effective ways.

Management of patients with type 2 diabetes and multiple chronic conditions: A Delphi consensus of the Spanish Society of Internal Medicine

AIMS

To develop consensus-based recommendations for the management of chronic complex patients with type 2 diabetes mellitus using a two round Delphi technique.

METHODS

Experts from the Diabetes and Obesity Working Group (DOWG) of the Spanish Society of Internal Medicine (SEMI) reviewed MEDLINE, PubMed, SCOPUS and Cochrane Library databases up to September 2014 to gather information on organization and health care management, stratification of therapeutic targets and therapeutic approach for glucose control in chronic complex patients with type 2 diabetes mellitus. A list of 6 recommendations was created and rated by a panel of 75 experts from the DOWG by email (first round) and by open discussion (second round). A written document was produced and sent back to DOWG experts for clarification purposes.

RESULTS

A high degree of consensus was achieved for all recommendations summarized as 1) there is a need to redesign and test new health care programs for chronic complex patients with type 2 diabetes mellitus; 2) therapeutic targets in patients with short life expectancy should be individualized in accordance to their personal, clinical and social characteristics; 3) patients with chronic complex conditions and type 2 diabetes mellitus should be stratified by hypoglycemia risk; 4) age and specific comorbidities should guide the objectives for glucose control; 5) the risk of hypoglycemia should be a key factor when choosing a treatment; and 6) basal insulin analogs compared to human insulin are cost-effective options.

CONCLUSION

The assessment and recommendations provided herein represent our best professional judgment based on current data and clinical experience.